AI

This startup’s new mechanistic interpretability tool lets you debug LLMs

MIT Tech Review · Thu, 30 Apr 2026 15:59:41 GMT

The San Francisco–based startup Goodfire just released a new tool, called Silico, that lets researchers and engineers peer inside an AI model and adjust its parameters—the settings that determine a model’s behavior—during training. This could give model makers more fine-grained c

Read original source Discuss with A.S.I.S